首页> 外文期刊>Journal of information and computational science >Tracking Fish Behavior for Anomaly Water Quality Evaluation
【24h】

Tracking Fish Behavior for Anomaly Water Quality Evaluation

机译:跟踪鱼类行为以评估异常水质

获取原文
获取原文并翻译 | 示例
           

摘要

A novel method for anomaly water quality assessment is proposed in this paper. Based on fish behavior in different water conditions, the study employs computer vision technology to detect and tract fish in a video sequence. With an established fish moving trajectory, six parameters are calculated, and among them, two parameters are selected as a feature vector corresponding to water conditions. The classification is conducted by Support Vector Machine (SVM) and BP neural network. The experimental results have shown that velocity and acceleration of fish movement can effectively reflect water quality difference, and SVM is superior to BP neural network in detecting anomaly water quality in this case, both in detection accuracy and computational cost.
机译:提出了一种新的异常水质评价方法。根据鱼类在不同水质条件下的行为,该研究采用计算机视觉技术来检测和跟踪视频序列中的鱼类。利用确定的鱼运动轨迹,计算六个参数,并在其中选择两个参数作为与水状况相对应的特征向量。通过支持向量机(SVM)和BP神经网络进行分类。实验结果表明,鱼类运动的速度和加速度可以有效地反映水质差异,在这种情况下,SVM在检测异常水质方面优于BP神经网络,无论是在检测精度还是计算成本上。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号